MCF-3D-CNN
MCF-3D-CNN copied to clipboard
Temporal-spatial Feature Learning of DCE-MR Images via 3DCNN
Temporal-spatial Feature Learning of DCE-MR Images via 3DCNN
Code for paper:
Requirements
Python 2.7
TensorFlow == 1.4.0
Keras == 2.2.4
For keras2.0.0 compatibility checkout tag keras2.0.0
Run:
- Start the training using:
python main.py -c configs/fusion_config.json # MCF-3D-CNN
python main.py -c configs/3dcnn_config.json # 3DCNN
- Start Tensorboard visualization using:
tensorboard --logdir=experiments/Year-Month-Day/Ex-name/logs
Data
The proprietary of the data belongs to Beijing Friendship Hospital. You can get access to anonymous data here.
![](https://github.com/xyj77/MCF-3D-CNN/raw/master/figures/DCE-MRI.png)
Tensor-based data representation
MCF-3DCNN architecture
Results
Tabel1 The results of discriminating the HCC and cirrhosis
Tabel2 The results of non-invasive assessment of HCC differentiation
Feature maps of C1 and C2 convolution layer
![](https://github.com/xyj77/MCF-3D-CNN/raw/master/figures/FeatureMaps.png)
One Vs. Other
A multi-classification problem is transformed into multiple binary classification problems. The results are as follow:
![](https://github.com/xyj77/MCF-3D-CNN/raw/master/figures/oneVsAllRes.jpg)
The average area under the ROC curve for 3DCNN for discriminating poorly, moderately and well differentiated HCCs.
![](https://github.com/xyj77/MCF-3D-CNN/raw/master/figures/oneVsAllROC.jpg)
Reference
Citation
If you use this code or data for your research, please cite our papers.
@inproceedings{IGTA 2018,
title={Temporal-Spatial Feature Learning of Dynamic Contrast Enhanced-MR Images via 3D Convolutional Neural Networks},
author={Jia X., Xiao Y., Yang D., Yang Z., Wang X., Liu Y},
booktitle={Image and Graphics Technologies and Applications. IGTA 2018. Communications in Computer and Information Science},
year={2018}
}
Da-wei Yang, Xi-bin Jia, Yu-jie Xiao, Xiao-pei Wang, Zhen-chang Wang, and Zheng-han Yang, “Noninvasive Evaluation of the Pathologic Grade of Hepatocellular Carcinoma Using MCF-3DCNN: A Pilot Study,” BioMed Research International, vol. 2019, Article ID 9783106, 12 pages, 2019. https://doi.org/10.1155/2019/9783106.